© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 8776
    Prev
    Next
    INDEX
    Explanations

    Now

    np_max-act · gemini-2.0-flash

    This neuron fires on promotional/time-of-announcement cue words—especially sentence-initial “Now” (and similar marketing lead-ins like “Good News,” “News Update,” “Includes,” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     REF
    -0.07
     약
    -0.06
     cherry
    -0.06
    ember
    -0.06
    tir
    -0.06
     Quad
    -0.06
    TPL
    -0.05
    �습니다
    -0.05
     배송
    -0.05
    -success
    -0.05
    POSITIVE LOGITS
     illustrator
    0.07
     Napoli
    0.07
     πλη
    0.07
    .reference
    0.07
    (bodyParser
    0.07
    .registry
    0.07
    (secret
    0.06
    опис
    0.06
    Now
    0.06
    姐
    0.06
    Activations Density 0.011%

    No Known Activations